Lyria 3 Clip vs Lyria 3.5: which one runs on Sume?
Google lists Lyria 3 Clip as a 30-second model and Lyria 3.5 as minutes long. Sume's Music Router routes lyria-3.5, lyria-3-pro or sume/music-auto.
Sume's Music Router does not list Lyria 3 Clip. Its routable ids are sume/music-auto (the default), lyria-3.5 and lyria-3-pro. Google's guide, read 2026-10-01, says Lyria 3 Clip makes 30-second clips (lyria-3-clip-preview) and Lyria 3.5 runs a couple of minutes.
Which Lyria models does Sume route?
Routable ids on Sume's Music Router, versus Google's listing.
| Model | Listed by Google | Routable on Sume |
|---|---|---|
| lyria-3-clip-preview | Yes, 30-second clips | No |
| lyria-3.5 | Yes | Yes |
| lyria-3-pro | Not covered here | Yes |
How do I see what Sume offers?
GET /v1/music-router/models lists the catalog. After a job, job.request.routed_model tells you which engine ran, which matters when you left the model on sume/music-auto.
What if I need 30 seconds?
Ask for it in the prompt with a timestamp marker such as [0:00-0:30], or cut a longer track with Timeline audio split. There is no duration field on Sume music.
Sources
Related posts
More in Models
- Lyria 3.5 takes 131,072 tokens; Sume music prompts, 5,000 chars
Google lists a 131,072 token input limit for Lyria 3.5. Sume's music prompt field takes 1 to 5,000 characters. What fits and how to trim.
- Lyria 3.5 takes up to 10 images; Sume music takes one image_url
Google's Lyria guide allows up to 10 images as input. Sume's music docs describe one optional public HTTPS image_url. What that changes.
- MAI-Transcribe-2 languages (60) vs Sume STT language hint
Microsoft's MAI-Transcribe-2 preview covers 60 languages. Sume STT 1.0 takes one optional language_code hint and auto-detects when you omit it.
- MAI-Transcribe-2 speaker diarization vs Sume STT: no speaker field
MAI-Transcribe-2 attributes each segment to a distinct speaker. Sume STT has no diarize field: provider knobs are fixed server-side and you get words[].
Written by Sume